A Variant of Azuma's Inequality for Martingales with Subgaussian Tails
classification
💻 cs.LG
math.PR
keywords
azumainequalitymartingalesrequirementsubgaussianvariantboundednessconcentration
read the original abstract
We provide a variant of Azuma's concentration inequality for martingales, in which the standard boundedness requirement is replaced by the milder requirement of a subgaussian tail.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
Offline KL-regularized MABs require sample complexity scaling as O(η S A C^π*/ε) for large regularization and Ω(S A C^π*/ε²) for small regularization, with matching lower bounds across the full range.
-
Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
A novel robust asynchronous Q-learning algorithm achieves finite-time convergence rates that match clean-data bounds up to an additive term proportional to the corruption fraction, with a matching information-theoreti...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.